Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multimodal Reasoning on R1-Onevision-Bench Math
Loading...
25.7
Accuracy
No Compression
22.788
23.544
24.3
25.056
Feb 10, 2026
Accuracy
Average Length
Ratio
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
Average Length
Ratio
No Compression
Base Model=Qwen2.5-VL
2026.02
25.7
629.5
24.5
Prune-on-Logic
Base Model=Qwen2.5-VL
2026.02
25.4
418.7
16.5
XMCC
Base Model=Qwen2.5-VL
2026.02
25.4
121.2
4.8
Prune-on-Logic
Base Model=Qwen3-VL
2026.02
25
428.9
17.2
StepEntropy
Base Model=Qwen2.5-VL
2026.02
24.9
399
16
No Compression
Base Model=Qwen3-VL
2026.02
24.8
617.7
24.9
XMCC
Base Model=Qwen3-VL
2026.02
24.5
120.6
4.9
StepEntropy
Base Model=Qwen3-VL
2026.02
22.9
397.7
17.4
Feedback
Search any
task
Search any
task